Corpus ID: 220665753

MovieNet: A Holistic Dataset for Movie Understanding

@article{Huang2020MovieNetAH,
  title={MovieNet: A Holistic Dataset for Movie Understanding},
  author={Q. Huang and Yu Xiong and Anyi Rao and Jiaze Wang and D. Lin},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.10937}
}
  • Q. Huang, Yu Xiong, +2 authors D. Lin
  • Published 2020
  • Computer Science
  • ArXiv
  • Recent years have seen remarkable advances in visual understanding. However, how to understand a story-based long video with artistic styles, e.g. movie, remains challenging. In this paper, we introduce MovieNet – a holistic dataset for movie understanding. MovieNet contains 1, 100 movies with a large amount of multi-modal data, e.g. trailers, photos, plot descriptions, etc.. Besides, different aspects of manual annotations are provided in MovieNet, including 1.1M characters with bounding boxes… CONTINUE READING
    A Unified Framework for Shot Type Classification Based on Subject Centric Lens
    • 5
    • PDF
    Placepedia: Comprehensive Place Understanding with Multi-Faceted Annotations
    • 2
    • PDF
    Online Multi-modal Person Search in Videos
    • 3
    • PDF
    Learn to Propagate Reliably on Noisy Affinity Graphs
    • 1
    • PDF
    Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
    • 5
    • PDF
    Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation
    • 4
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 88 REFERENCES
    Moviescope: Large-scale Analysis of Movies using Multiple Modalities
    • 7
    • Highly Influential
    • PDF
    A dataset for Movie Description
    • 220
    • Highly Influential
    • PDF
    Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books
    • 719
    • PDF
    A Local-to-Global Approach to Multi-Modal Movie Scene Segmentation
    • 7
    • PDF
    From Trailers to Storylines: An Efficient Way to Learn from Movies
    • 6
    • PDF
    Holistic Large Scale Video Understanding
    • 10
    • Highly Influential
    Using context saliency for movie shot classification
    • 17
    • PDF
    A Graph-Based Framework to Bridge Movies and Synopses
    • 10
    • PDF
    A Unified Framework for Shot Type Classification Based on Subject Centric Lens
    • 5
    • PDF
    MSR-VTT: A Large Video Description Dataset for Bridging Video and Language
    • 381
    • PDF